Skip to content

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

feat(blocks): Add Nano Banana 2 to image generator, customizer, and editor blocks (#12218)

Ottoe65747216217
diff --git a/autogpt_platform/backend/backend/blocks/ai_image_customizer.py b/autogpt_platform/backend/backend/blocks/ai_image_customizer.py
index 402e520ea0..f63e6833dc 100644
--- a/autogpt_platform/backend/backend/blocks/ai_image_customizer.py
+++ b/autogpt_platform/backend/backend/blocks/ai_image_customizer.py
@@ -27,6 +27,7 @@ from backend.util.file import MediaFileType, store_media_file
class GeminiImageModel(str, Enum):
NANO_BANANA = "google/nano-banana"
NANO_BANANA_PRO = "google/nano-banana-pro"
+ NANO_BANANA_2 = "google/nano-banana-2"
class AspectRatio(str, Enum):
@@ -77,7 +78,7 @@ class AIImageCustomizerBlock(Block):
)
model: GeminiImageModel = SchemaField(
description="The AI model to use for image generation and editing",
- default=GeminiImageModel.NANO_BANANA,
+ default=GeminiImageModel.NANO_BANANA_2,
title="Model",
)
images: list[MediaFileType] = SchemaField(
@@ -103,7 +104,7 @@ class AIImageCustomizerBlock(Block):
super().__init__(
id="d76bbe4c-930e-4894-8469-b66775511f71",
description=(
- "Generate and edit custom images using Google's Nano-Banana model from Gemini 2.5. "
+ "Generate and edit custom images using Google's Nano-Banana models from Gemini. "
"Provide a prompt and optional reference images to create or modify images."
),
categories={BlockCategory.AI, BlockCategory.MULTIMEDIA},
@@ -111,7 +112,7 @@ class AIImageCustomizerBlock(Block):
output_schema=AIImageCustomizerBlock.Output,
test_input={
"prompt": "Make the scene more vibrant and colorful",
- "model": GeminiImageModel.NANO_BANANA,
+ "model": GeminiImageModel.NANO_BANANA_2,
"images": [],
"aspect_ratio": AspectRatio.MATCH_INPUT_IMAGE,
"output_format": OutputFormat.JPG,
diff --git a/autogpt_platform/backend/backend/blocks/ai_image_generator_block.py b/autogpt_platform/backend/backend/blocks/ai_image_generator_block.py
index fcea24fb01..864abee530 100644
--- a/autogpt_platform/backend/backend/blocks/ai_image_generator_block.py
+++ b/autogpt_platform/backend/backend/blocks/ai_image_generator_block.py
@@ -115,6 +115,7 @@ class ImageGenModel(str, Enum):
RECRAFT = "Recraft v3"
SD3_5 = "Stable Diffusion 3.5 Medium"
NANO_BANANA_PRO = "Nano Banana Pro"
+ NANO_BANANA_2 = "Nano Banana 2"
class AIImageGeneratorBlock(Block):
@@ -131,7 +132,7 @@ class AIImageGeneratorBlock(Block):
)
model: ImageGenModel = SchemaField(
description="The AI model to use for image generation",
- default=ImageGenModel.SD3_5,
+ default=ImageGenModel.NANO_BANANA_2,
title="Model",
)
size: ImageSize = SchemaField(
@@ -165,7 +166,7 @@ class AIImageGeneratorBlock(Block):
test_input={
"credentials": TEST_CREDENTIALS_INPUT,
"prompt": "An octopus using a laptop in a snowy forest with 'AutoGPT' clearly visible on the screen",
- "model": ImageGenModel.RECRAFT,
+ "model": ImageGenModel.NANO_BANANA_2,
"size": ImageSize.SQUARE,
"style": ImageStyle.REALISTIC,
},
@@ -179,7 +180,9 @@ class AIImageGeneratorBlock(Block):
],
test_mock={
# Return a data URI directly so store_media_file doesn't need to download
- "_run_client": lambda *args, **kwargs: "data:image/webp;base64,UklGRiQAAABXRUJQVlA4IBgAAAAwAQCdASoBAAEAAQAcJYgCdAEO"
+ "_run_client": lambda *args, **kwargs: (
+ "data:image/webp;base64,UklGRiQAAABXRUJQVlA4IBgAAAAwAQCdASoBAAEAAQAcJYgCdAEO"
+ )
},
)
@@ -280,17 +283,24 @@ class AIImageGeneratorBlock(Block):
)
return output
- elif input_data.model == ImageGenModel.NANO_BANANA_PRO:
- # Use Nano Banana Pro (Google Gemini 3 Pro Image)
+ elif input_data.model in (
+ ImageGenModel.NANO_BANANA_PRO,
+ ImageGenModel.NANO_BANANA_2,
+ ):
+ # Use Nano Banana models (Google Gemini image variants)
+ model_map = {
+ ImageGenModel.NANO_BANANA_PRO: "google/nano-banana-pro",
+ ImageGenModel.NANO_BANANA_2: "google/nano-banana-2",
+ }
input_params = {
"prompt": modified_prompt,
"aspect_ratio": SIZE_TO_NANO_BANANA_RATIO[input_data.size],
- "resolution": "2K", # Default to 2K for good quality/cost balance
+ "resolution": "2K",
"output_format": "jpg",
- "safety_filter_level": "block_only_high", # Most permissive
+ "safety_filter_level": "block_only_high",
}
output = await self._run_client(
- credentials, "google/nano-banana-pro", input_params
+ credentials, model_map[input_data.model], input_params
)
return output
diff --git a/autogpt_platform/backend/backend/blocks/flux_kontext.py b/autogpt_platform/backend/backend/blocks/flux_kontext.py
index f2b35aee40..7190cde8d6 100644
--- a/autogpt_platform/backend/backend/blocks/flux_kontext.py
+++ b/autogpt_platform/backend/backend/blocks/flux_kontext.py
@@ -34,17 +34,29 @@ TEST_CREDENTIALS_INPUT = {
"provider": TEST_CREDENTIALS.provider,
"id": TEST_CREDENTIALS.id,
"type": TEST_CREDENTIALS.type,
- "title": TEST_CREDENTIALS.type,
+ "title": TEST_CREDENTIALS.title,
}
-class FluxKontextModelName(str, Enum):
- PRO = "Flux Kontext Pro"
- MAX = "Flux Kontext Max"
+class ImageEditorModel(str, Enum):
+ FLUX_KONTEXT_PRO = "Flux Kontext Pro"
+ FLUX_KONTEXT_MAX = "Flux Kontext Max"
+ NANO_BANANA_PRO = "Nano Banana Pro"
+ NANO_BANANA_2 = "Nano Banana 2"
@property
def api_name(self) -> str:
- return f"black-forest-labs/flux-kontext-{self.name.lower()}"
+ _map = {
+ "FLUX_KONTEXT_PRO": "black-forest-labs/flux-kontext-pro",
+ "FLUX_KONTEXT_MAX": "black-forest-labs/flux-kontext-max",
+ "NANO_BANANA_PRO": "google/nano-banana-pro",
+ "NANO_BANANA_2": "google/nano-banana-2",
+ }
+ return _map[self.name]
+
+
+# Keep old name as alias for backwards compatibility
+FluxKontextModelName = ImageEditorModel
class AspectRatio(str, Enum):
@@ -69,7 +81,7 @@ class AIImageEditorBlock(Block):
credentials: CredentialsMetaInput[
Literal[ProviderName.REPLICATE], Literal["api_key"]
] = CredentialsField(
- description="Replicate API key with permissions for Flux Kontext models",
+ description="Replicate API key with permissions for Flux Kontext and Nano Banana models",
)
prompt: str = SchemaField(
description="Text instruction describing the desired edit",
@@ -87,14 +99,14 @@ class AIImageEditorBlock(Block):
advanced=False,
)
seed: Optional[int] = SchemaField(
- description="Random seed. Set for reproducible generation",
+ description="Random seed. Set for reproducible generation (Flux Kontext only; ignored by Nano Banana models)",
default=None,
title="Seed",
advanced=True,
)
- model: FluxKontextModelName = SchemaField(
+ model: ImageEditorModel = SchemaField(
description="Model variant to use",
- default=FluxKontextModelName.PRO,
+ default=ImageEditorModel.NANO_BANANA_2,
title="Model",
)
@@ -107,7 +119,7 @@ class AIImageEditorBlock(Block):
super().__init__(
id="3fd9c73d-4370-4925-a1ff-1b86b99fabfa",
description=(
- "Edit images using BlackForest Labs' Flux Kontext models. Provide a prompt "
+ "Edit images using Flux Kontext or Google Nano Banana models. Provide a prompt "
"and optional reference image to generate a modified image."
),
categories={BlockCategory.AI, BlockCategory.MULTIMEDIA},
@@ -118,7 +130,7 @@ class AIImageEditorBlock(Block):
"input_image": "data:image/png;base64,MQ==",
"aspect_ratio": AspectRatio.MATCH_INPUT_IMAGE,
"seed": None,
- "model": FluxKontextModelName.PRO,
+ "model": ImageEditorModel.NANO_BANANA_2,
"credentials": TEST_CREDENTIALS_INPUT,
},
test_output=[
@@ -127,7 +139,9 @@ class AIImageEditorBlock(Block):
],
test_mock={
# Use data URI to avoid HTTP requests during tests
- "run_model": lambda *args, **kwargs: "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==",
+ "run_model": lambda *args, **kwargs: (
+ "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg=="
+ ),
},
test_credentials=TEST_CREDENTIALS,
)
@@ -142,7 +156,7 @@ class AIImageEditorBlock(Block):
) -> BlockOutput:
result = await self.run_model(
api_key=credentials.api_key,
- model_name=input_data.model.api_name,
+ model=input_data.model,
prompt=input_data.prompt,
input_image_b64=(
await store_media_file(
@@ -169,7 +183,7 @@ class AIImageEditorBlock(Block):
async def run_model(
self,
api_key: SecretStr,
- model_name: str,
+ model: ImageEditorModel,
prompt: str,
input_image_b64: Optional[str],
aspect_ratio: str,
@@ -178,12 +192,29 @@ class AIImageEditorBlock(Block):
graph_exec_id: str,
) -> MediaFileType:
client = ReplicateClient(api_token=api_key.get_secret_value())
- input_params = {
- "prompt": prompt,
- "input_image": input_image_b64,
- "aspect_ratio": aspect_ratio,
- **({"seed": seed} if seed is not None else {}),
- }
+ model_name = model.api_name
+
+ is_nano_banana = model in (
+ ImageEditorModel.NANO_BANANA_PRO,
+ ImageEditorModel.NANO_BANANA_2,
+ )
+ if is_nano_banana:
+ input_params: dict = {
+ "prompt": prompt,
+ "aspect_ratio": aspect_ratio,
+ "output_format": "jpg",
+ "safety_filter_level": "block_only_high",
+ }
+ # NB API expects "image_input" as a list, unlike Flux's single "input_image"
+ if input_image_b64:
+ input_params["image_input"] = [input_image_b64]
+ else:
+ input_params = {
+ "prompt": prompt,
+ "input_image": input_image_b64,
+ "aspect_ratio": aspect_ratio,
+ **({"seed": seed} if seed is not None else {}),
+ }
try:
output: FileOutput | list[FileOutput] = await client.async_run( # type: ignore
diff --git a/autogpt_platform/backend/backend/data/block_cost_config.py b/autogpt_platform/backend/backend/data/block_cost_config.py
index 36e7228f7b..a3a264b57b 100644
--- a/autogpt_platform/backend/backend/data/block_cost_config.py
+++ b/autogpt_platform/backend/backend/data/block_cost_config.py
@@ -423,7 +423,7 @@ BLOCK_COSTS: dict[Type[Block], list[BlockCost]] = {
BlockCost(
cost_amount=10,
cost_filter={
- "model": FluxKontextModelName.PRO.api_name,
+ "model": FluxKontextModelName.FLUX_KONTEXT_PRO,
"credentials": {
"id": replicate_credentials.id,
"provider": replicate_credentials.provider,
@@ -434,7 +434,29 @@ BLOCK_COSTS: dict[Type[Block], list[BlockCost]] = {
BlockCost(
cost_amount=20,
cost_filter={
- "model": FluxKontextModelName.MAX.api_name,
+ "model": FluxKontextModelName.FLUX_KONTEXT_MAX,
+ "credentials": {
+ "id": replicate_credentials.id,
+ "provider": replicate_credentials.provider,
+ "type": replicate_credentials.type,
+ },
+ },
+ ),
+ BlockCost(
+ cost_amount=14, # Nano Banana Pro
+ cost_filter={
+ "model": FluxKontextModelName.NANO_BANANA_PRO,
+ "credentials": {
+ "id": replicate_credentials.id,
+ "provider": replicate_credentials.provider,
+ "type": replicate_credentials.type,
+ },
+ },
+ ),
+ BlockCost(
+ cost_amount=14, # Nano Banana 2
+ cost_filter={
+ "model": FluxKontextModelName.NANO_BANANA_2,
"credentials": {
"id": replicate_credentials.id,
"provider": replicate_credentials.provider,
@@ -632,6 +654,17 @@ BLOCK_COSTS: dict[Type[Block], list[BlockCost]] = {
},
},
),
+ BlockCost(
+ cost_amount=14, # Nano Banana 2: same pricing tier as Pro
+ cost_filter={
+ "model": ImageGenModel.NANO_BANANA_2,
+ "credentials": {
+ "id": replicate_credentials.id,
+ "provider": replicate_credentials.provider,
+ "type": replicate_credentials.type,
+ },
+ },
+ ),
],
AIImageCustomizerBlock: [
BlockCost(
@@ -656,6 +689,17 @@ BLOCK_COSTS: dict[Type[Block], list[BlockCost]] = {
},
},
),
+ BlockCost(
+ cost_amount=14, # Nano Banana 2: same pricing tier as Pro
+ cost_filter={
+ "model": GeminiImageModel.NANO_BANANA_2,
+ "credentials": {
+ "id": replicate_credentials.id,
+ "provider": replicate_credentials.provider,
+ "type": replicate_credentials.type,
+ },
+ },
+ ),
],
VideoNarrationBlock: [
BlockCost(
diff --git a/docs/integrations/README.md b/docs/integrations/README.md
index 029a86327f..1ac7fc763a 100644
--- a/docs/integrations/README.md
+++ b/docs/integrations/README.md
@@ -209,8 +209,8 @@ Below is a comprehensive list of all available blocks, categorized by their prim
| [AI Ad Maker Video Creator](block-integrations/llm.md#ai-ad-maker-video-creator) | Creates an AI‑generated 30‑second advert (text + images) |
| [AI Condition](block-integrations/llm.md#ai-condition) | Uses AI to evaluate natural language conditions and provide conditional outputs |
| [AI Conversation](block-integrations/llm.md#ai-conversation) | A block that facilitates multi-turn conversations with a Large Language Model (LLM), maintaining context across message exchanges |
-| [AI Image Customizer](block-integrations/llm.md#ai-image-customizer) | Generate and edit custom images using Google's Nano-Banana model from Gemini 2 |
-| [AI Image Editor](block-integrations/llm.md#ai-image-editor) | Edit images using BlackForest Labs' Flux Kontext models |
+| [AI Image Customizer](block-integrations/llm.md#ai-image-customizer) | Generate and edit custom images using Google's Nano-Banana models from Gemini |
+| [AI Image Editor](block-integrations/llm.md#ai-image-editor) | Edit images using Flux Kontext or Google Nano Banana models |
| [AI Image Generator](block-integrations/llm.md#ai-image-generator) | Generate images using various AI models through a unified interface |
| [AI List Generator](block-integrations/llm.md#ai-list-generator) | A block that creates lists of items based on prompts using a Large Language Model (LLM), with optional source data for context |
| [AI Music Generator](block-integrations/llm.md#ai-music-generator) | This block generates music using Meta's MusicGen model on Replicate |
diff --git a/docs/integrations/block-integrations/llm.md b/docs/integrations/block-integrations/llm.md
index e17b322011..b506cfe0bc 100644
--- a/docs/integrations/block-integrations/llm.md
+++ b/docs/integrations/block-integrations/llm.md
@@ -125,7 +125,7 @@ Creating an interactive chatbot that can maintain context over multiple exchange
## AI Image Customizer
### What it is
-Generate and edit custom images using Google's Nano-Banana model from Gemini 2.5. Provide a prompt and optional reference images to create or modify images.
+Generate and edit custom images using Google's Nano-Banana models from Gemini. Provide a prompt and optional reference images to create or modify images.
### How it works
<!-- MANUAL: how_it_works -->
@@ -139,7 +139,7 @@ Configure aspect ratio to match your needs and choose between JPG or PNG output
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| prompt | A text description of the image you want to generate | str | Yes |
-| model | The AI model to use for image generation and editing | "google/nano-banana" \| "google/nano-banana-pro" | No |
+| model | The AI model to use for image generation and editing | "google/nano-banana" \| "google/nano-banana-pro" \| "google/nano-banana-2" | No |
| images | Optional list of input images to reference or modify | List[str (file)] | No |
| aspect_ratio | Aspect ratio of the generated image | "match_input_image" \| "1:1" \| "2:3" \| "3:2" \| "3:4" \| "4:3" \| "4:5" \| "5:4" \| "9:16" \| "16:9" \| "21:9" | No |
| output_format | Format of the output image | "jpg" \| "png" | No |
@@ -165,13 +165,13 @@ Configure aspect ratio to match your needs and choose between JPG or PNG output
## AI Image Editor
### What it is
-Edit images using BlackForest Labs' Flux Kontext models. Provide a prompt and optional reference image to generate a modified image.
+Edit images using Flux Kontext or Google Nano Banana models. Provide a prompt and optional reference image to generate a modified image.
### How it works
<!-- MANUAL: how_it_works -->
-This block uses BlackForest Labs' Flux Kontext models for context-aware image editing. Describe the desired edit in the prompt, and optionally provide an input image to modify.
+This block uses BlackForest Labs' Flux Kontext or Google's Nano Banana models for context-aware image editing. Describe the desired edit in the prompt, and optionally provide an input image to modify.
-Choose between Flux Kontext Pro or Max for different quality/speed tradeoffs. Set a seed for reproducible results across multiple runs.
+Choose between Flux Kontext Pro, Max, or Nano Banana models for different quality/speed tradeoffs. Set a seed for reproducible results across multiple runs (Flux Kontext only).
<!-- END MANUAL -->
### Inputs
@@ -181,8 +181,8 @@ Choose between Flux Kontext Pro or Max for different quality/speed tradeoffs. Se
| prompt | Text instruction describing the desired edit | str | Yes |
| input_image | Reference image URI (jpeg, png, gif, webp) | str (file) | No |
| aspect_ratio | Aspect ratio of the generated image | "match_input_image" \| "1:1" \| "16:9" \| "9:16" \| "4:3" \| "3:4" \| "3:2" \| "2:3" \| "4:5" \| "5:4" \| "21:9" \| "9:21" \| "2:1" \| "1:2" | No |
-| seed | Random seed. Set for reproducible generation | int | No |
-| model | Model variant to use | "Flux Kontext Pro" \| "Flux Kontext Max" | No |
+| seed | Random seed. Set for reproducible generation (Flux Kontext only; ignored by Nano Banana models) | int | No |
+| model | Model variant to use | "Flux Kontext Pro" \| "Flux Kontext Max" \| "Nano Banana Pro" \| "Nano Banana 2" | No |
### Outputs
@@ -219,7 +219,7 @@ The unified interface allows switching between models without changing your work
| Input | Description | Type | Required |
|-------|-------------|------|----------|
| prompt | Text prompt for image generation | str | Yes |
-| model | The AI model to use for image generation | "Flux 1.1 Pro" \| "Flux 1.1 Pro Ultra" \| "Recraft v3" \| "Stable Diffusion 3.5 Medium" \| "Nano Banana Pro" | No |
+| model | The AI model to use for image generation | "Flux 1.1 Pro" \| "Flux 1.1 Pro Ultra" \| "Recraft v3" \| "Stable Diffusion 3.5 Medium" \| "Nano Banana Pro" \| "Nano Banana 2" | No |
| size | Format of the generated image: - Square: Perfect for profile pictures, icons - Landscape: Traditional photo format - Portrait: Vertical photos, portraits - Wide: Cinematic format, desktop wallpapers - Tall: Mobile wallpapers, social media stories | "square" \| "landscape" \| "portrait" \| "wide" \| "tall" | No |
| style | Visual style for the generated image | "any" \| "realistic_image" \| "realistic_image/b_and_w" \| "realistic_image/hdr" \| "realistic_image/natural_light" \| "realistic_image/studio_portrait" \| "realistic_image/enterprise" \| "realistic_image/hard_flash" \| "realistic_image/motion_blur" \| "digital_illustration" \| "digital_illustration/pixel_art" \| "digital_illustration/hand_drawn" \| "digital_illustration/grain" \| "digital_illustration/infantile_sketch" \| "digital_illustration/2d_art_poster" \| "digital_illustration/2d_art_poster_2" \| "digital_illustration/handmade_3d" \| "digital_illustration/hand_drawn_outline" \| "digital_illustration/engraving_color" | No |